Search NASA⌕ Search

SEARCH · Search NASA

Results for “operator inference”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 217 records · Page 12

Neural network approximation of Bayesian models for the inference of ion and electron temperature profiles at W7-X

Here, we describe a method for training a neural network (NN) to approximate the full model Bayesian inference of plasma profiles from x-ray imaging diagnostic measurements. The modeling is carried out within the Minerva Bayesian modeling framework where models are defined as a set of assumptions, prior beliefs on parameter values and physics knowledge. The goal is to use NNs for fast ion and electron temperature profile inversion from measured image data. The NN is trained solely on artificial data generated by sampling from the joint distribution of the free parameters and model predictions. The training is carried out in such a way that the mapping learned by the network constitutes an approximation of the full model Bayesian inference. The analysis is carried out on images constituted of 20 × 195 pixels corresponding to binned lines of sight and spectral channels, respectively. Through the full model inference, it is possible to infer electron and ion temperature profiles as well as impurity density profiles. When the network is utilized for the inference of the temperature profiles, the analysis time can be reduced down to a few tens of microseconds for a single time point, which is a drastic improvement if compared to the ≈4 h long Bayesian inference. The procedure developed for the generation of the training set does not rely on diagnostic-specific features, and therefore it is in principle applicable to any other model developed within the Minerva framework. The trained NN has been tested on data collected during the first operational campaign at W7-X, and compared to the full model Bayesian inference results.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

A one-dimensional theory for Higgs branch operators

We use supersymmetric localization to calculate correlation functions of half-BPS local operators in 3d N=4 superconformal field theories whose Lagrangian descriptions consist of vectormultiplets coupled to hypermultiplets. The operators we primarily study are certain twisted linear combinations of Higgs branch operators that can be inserted anywhere along a given line. These operators are constructed from the hypermultiplet scalars. They form a one-dimensional non-commutative operator algebra with topological correlation functions. The 2- and 3-point functions of Higgs branch operators in the full 3d N=4 theory can be simply inferred from the 1d topological algebra. After conformally mapping the 3d superconformal field theory from flat space to a round three-sphere, we preform supersymmetric localization using a supercharge that does not belong to any 3d N=2 subalgebra of the N=4 algebra. The result is a simple model that can be used to calculate correlation functions in the 1d topological algebra mentioned above. This model is a 1d Gaussian theory coupled to a matrix model, and it can be viewed as a gauge-fixed version of a topological gauged quantum mechanics. Our results generalize to non-conformal theories on S3 that contain real mass and Fayet-Iliopolous parameters. In conclusion, we also provide partial results in the 1d topological algebra associated with the Coulomb branch, where we calculate correlation functions of local operators built from the vectormultiplet scalars.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Application of ultraviolet reflectivity measurements from Nimbus-7 to determine cloud amount

A technique is described that uses scene reflectivity derived from the Total Ozone Mapping Spectrometer (TOMS) measurements from aboard the Nimbus-7 satellite to improve the estimation of cloud amounts from the data taken by the Temperature Humidity IR Radiometer (THIR) onboard the same satellite. TOMS operates in six 1 nm wide spectral bands in the UV (380, 360, 340, 331, 318, and 313 nm) and provides information for inference of directional albedos. Moreover, the features of the TOMS images are paralleled with those obtained by the Geostationary Operational Environmental Satellite (GEOS) visible images. It is noted that by use of such a multisensor approach relatively thin or broken low clouds (below 2 km) can be detected with an rms error of about 10 percent when compared to the GOES visible and IR images.

Bhartia, P. K.↗

Real-time inference and extrapolation with Time-Conditioned UNet: Applications in hypersonic flows, incompressible flows, and global temperature forecasting

Neural Operators are fast and accurate surrogates for nonlinear mappings between functional spaces within training domains. Extrapolation beyond the training domain remains a grand challenge across all application areas. We present Time-Conditioned UNet (TC-UNet) as an operator learning method to solve time-dependent PDEs continuously in time without any temporal discretization, including in extrapolation scenarios. TC-UNet incorporates the temporal evolution of the PDE into its architecture by combining a parameter conditioning approach with the attention mechanism from the Transformer architecture. After training, TC-UNet makes real-time inferences on an arbitrary temporal grid. We demonstrate its extrapolation capability on a climate problem by estimating the global temperature for several years and also for inviscid hypersonic flow around a double cone. We propose different training strategies involving temporal bundling and sub-sampling. We demonstrate performance improvements for several benchmarks, performing extrapolation for long time intervals and zero-shot super-resolution time.

Deep learning↗

A survey on degradation modeling, prognosis, and prognostics-driven maintenance in wind energy systems

Wind energy generation proliferated over the past decades, introducing unique challenges and opportunities for failure prediction, operation and maintenance. Decision-makers are continuously looking into new methods to infer failure mechanisms and behaviors of wind turbine components to detect and intervene in the failures before they happen. Evidently, degradation modeling and prognosis become engaging topics for researchers and practitioners to prevent catastrophic failures. Prognostics-driven approaches predict the time of failure for the components (e.g., predicting remaining useful life), which provides significant insights for scheduling of operations and maintenance activities. Integrating these prognostics-driven insights into wind farm operations and maintenance presents a substantial challenge, demanding careful consideration of numerous factors such as accessibility, crew routing, and spare part logistics. This study provides state-of-the-art review for degradation modeling, prognosis, and prognostics-driven maintenance techniques for wind energy systems. The discussed techniques align with the United Nations' sustainable development goals, in particular Goal 7 (Affordable and Clean Energy), by enhancing effectiveness and sustainability of wind energy operations. This work also showcases open research questions related to degradation modeling, prognosis, and prognostics-driven maintenance.

Altinpulluk, Nur Banu↗

Using Formal Grammars to Predict I/O Behaviors in HPC: The Omnisc'IO Approach

The increasing gap between the computation performance of post-petascale machines and the performance of their I/O subsystem has motivated many I/O optimizations including prefetching, caching, and scheduling. In order to further improve these techniques, modeling and predicting spatial and temporal I/O patterns of HPC applications as they run has become crucial. In this paper we present Omnisc'IO, an approach that builds a grammar-based model of the I/O behavior of HPC applications and uses it to predict when future I/O operations will occur, and where and how much data will be accessed. To infer grammars, Omnisc'IO is based on StarSequitur, a novel algorithm extending Nevill-Manning's Sequitur algorithm. Omnisc'IO is transparently integrated into the POSIX and MPI I/O stacks and does not require any modification in applications or higher-level I/O libraries. It works without any prior knowledge of the application and converges to accurate predictions of any N future I/O operations within a couple of iterations. Its implementation is efficient in both computation time and memory footprint.

97 MATHEMATICS AND COMPUTING↗

Analog Systems for Edge Optimization

Over the past decade, analog computing has the subject of substantial research interest providing a path toward improved computational efficiency in the post-Dennard era. Analog matrix vector multiplication (MVM) accelerators provide a popular approach given the ubiquity of MVM operations in numerous applications. However, historically analog computing systems can struggle with applications requiring high precision due to the inherent susceptibility of these systems to analog non-idealities. Therefore, prior work on analog systems has focused either on applications known to be tolerant of limited precision (e.g., neural network inference), or using expensive techniques to emulate high-precision using many analog MVM operations. In this work, we propose an alternative approach. Motivated by recent advances in inexact nonlinear solvers and optimizers, we explore the potential of co-designing optimization algorithms which can take full advantage of the fundamentally inexact analog MVM operations. To enable these co-designed algorithms we also develop a general mathematical theory of the precision and energy efficiency of analog operations, and a new system architecture for tightly-coupled analog and digital computation. Finally, we examine the applicability of analog computing to a wider class of symmetric positive definite systems and find potential in using analog operations as a sparse approximate inverse preconditioner. With these core innovations, this project provides a path toward effectively implementing optimization algorithms on power-constrained autonomous and semi-autonomous systems.

97 MATHEMATICS AND COMPUTING↗

Implementation of a Binary Neural Network on a Passive Array of Magnetic Tunnel Junctions

The increasing scale of neural networks and their growing application space have produced demand for more energy- and memory-efficient artificial-intelligence-specific hardware. Avenues to mitigate the main issue, the von Neumann bottleneck, include in-memory and near-memory architectures, as well as algorithmic approaches. In this report we leverage the low-power and the inherently binary operation of magnetic tunnel junctions (MTJs) to demonstrate neural network hardware inference based on passive arrays of MTJs. In general, transferring a trained network model to hardware for inference is confronted by degradation in performance due to device-to-device variations, write errors, parasitic resistance, and nonidealities in the substrate. To quantify the effect of these hardware realities, we benchmark 300 unique weight matrix solutions of a two-layer perceptron to classify the Wine dataset for both classification accuracy and write fidelity. Despite device imperfections, we achieve software-equivalent accuracy of up to 95.3% with proper tuning of network parameters in 15 x 15 MTJ arrays having a range of device sizes. The success of this tuning process shows that new metrics are needed to characterize the performance and quality of networks reproduced in mixed signal hardware.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Diurnal variability of regional cloud radiative parameters from geostationary satellite data

In the discussed study, Geostationary Operational Environmental Satellite visible and infrared brightness measurements are used to infer regional cloud cover and several associated radiative parameters on an hourly basis. Several techniques are utilized to derive the parameters of interest. These parameters include the areal cloud fraction, cloud-atmosphere albedo, surface-atmosphere albedo, and equivalent blackbody surface and cloud-top temperatures. Attention is given to clear radiance temperature determinations, surface temperature modeling, the infrared threshold method, narrowband-broadband correlations, and albedo determination. Monthly mean values were computed for each parameter as a function of local time. Cloud amounts and temperatures are considered along with longwave emission and shortwave albedo, and composite results.

Minnis, P.↗

Transfer-AE: A novel autoencoder-based impact detection model for structural digital twin

Accurately detecting the location and intensity of impacts is crucial for ensuring structural safety. Currently, AI-based structural impact detection methods are widely used for their excellent detection accuracy. However, their generalization capability is limited by the scenarios present in the training data. Many complex and dangerous impact scenarios are difficult to conduct real-world experiments on to collect sufficient samples. To capture all impact scenarios and fully leverage the advantages of AI-based detection technologies, advanced methods involve combining real-world structural monitoring data with corresponding numerical models to construct digital twins. These methods continuously refine the created numerical models with limited real-world data and provide diverse impact scenarios through numerical model simulations. However, there are inevitable differences between digital models and physical models that are challenging to correct through mechanical means. This discrepancy in data distribution between the two models significantly hinders the application of digital twin technology in impact/event identification tasks. To address this challenge, this study proposes a novel model based on autoencoders, named Transfer-AE. Transfer-AE encodes the common features of digital twins in the latent space to bridge the uncertainty gap at a macro scale between numerical models and physical models and synchronously fits the magnitude and location of the impact load in the decoder. This enables consistent detection results for the same impact event, whether the sample comes from the numerical model or the physical model. Transfer-AE includes two operating modes: Mode 1 has a fixed computational complexity with stable inference speed, but the training cost and difficulty increase with data distribution. Mode 2's computational complexity increases with data distribution, but it has a fixed training cost and speed. In both cases involving the geodesic dome structure simulating a deep space habitat and the IASC-ASCE benchmark structure, Transfer-AE demonstrated the best performance in impact localization and quantification tasks compared to mainstream domain-adaptive transfer models.

Chengjia Han↗

Storage Requirements for Grid Integration of Marine Renewable Energy - a Parametric Study

Marine resources such as waves and tides house immense potential to serve as energy-rich sources of renewable power generation. They are known to be highly available,persistent and predictable in nature. Therefore, these can serve as one of the critical components for a primarily renewable energy-driven, resilient and robust future power grid. Although some inherent temporal characteristics of these resources lend themselves favorably to potential grid applications, the inclusion of storage allows the benefits and value streams to become realized more fully. In this paper, we present a framework for assessing impact of marine energy resources inclusion on the overall load generation balance and its impact on the relevant storage requirements to obtain the desired level of renewable energy penetration. From this study, we can critically infer two main points - (a) the relative storage requirements for grid operations with and without marine energy, and (b) the avoided cost of storage by including marine energy into the generation mix. We demonstrate our framework for two different locations across the United States.

Hanif, Sarmad↗

Koopman Operator Methods for Global Phase Space Exploration of Equivariant Dynamical Systems

In this paper, we develop the Koopman operator theory for dynamical systems with symmetry. In particular, we investigate how the Koopman operator and eigenfunctions behave under the action of the symmetry group of the underlying dynamical system. Further, exploring the underlying symmetry, we propose an algorithm to construct a global Koopman operator from local Koopman operators. In particular, we show, by exploiting the symmetry, data from all the invariant sets are not required for constructing the global Koopman operator; that is, local knowledge of the system is enough to infer the global dynamics.

Sinha, Subhrajit↗

Reasoning about procedural knowledge

A crucial aspect of automated reasoning about space operations is that knowledge of the problem domain is often procedural in nature - that is, the knowledge is often in the form of sequences of actions or procedures for achieving given goals or reacting to certain situations. In this paper a system is described that explicitly represents and reasons about procedural knowledge. The knowledge representation used is sufficiently rich to describe the effects of arbitrary sequences of tests and actions, and the inference mechanism provides a means for directly using this knowledge to reach desired operational goals. Furthermore, the representation has a declarative semantics that provides for incremental changes to the system, rich explanatory capabilities, and verifiability. The approach also provides a mechanism for reasoning about the use of this knowledge, thus enabling the system to choose effectively between alternative courses of action.

Georgeff, M. P.↗

Autonomous System Subversion Tactics: Prototypes and Recommended Countermeasures

One of the fielding requirements for Advanced and Small Modular Reactors (AR/SMR) is the ability to support remote and autonomous operations. Autonomous Control Systems (ACS) are found on platforms such as Autonomous Space Vehicles, Cruise Missiles, and advanced driver-assistance systems. Each of these ACS implementations depends upon a set of decision support subsystems responsible for supporting Autonomous Mission Managers (names vary based upon field and author preferences). These Autonomous Mission Managers receive inputs from system sensors (e.g., LIDAR collection from an automobile travelling down a street; transients from a nuclear reactor), and perform a set of classifications (e.g., Red Traffic Light; Small Pedestrian at 10m; Load Rejection; Single Coolant Pump Trip), and then use these classifications in combination with recommendation algorithms to achieve platform goals (e.g., Stop the Vehicle at the Traffic Light, Avoid the Small Pedestrian; Trip the Reactor to prevent a Safety Event). The design, implementation, and fielding of an ACS capability will alter the cyber-attack surface such that existing risk management plans will need to be updated to include how to protect and defend against data-science and decision-support-system attack classes. These attack classes would include protection of the design and training environments where algorithm selection and testing and training data would be obvious attack vectors. These attack classes would also require an informed set of detection and response procedures to identify anomalous behaviors and document best practices for anomaly assessment and vulnerability mitigation and remediation. Last year we published a Cyber Threat Assessment Methodology for Autonomous and Remote Operations for AR/SMRs along with a companion publication on Cyber Attack and Defense Use Cases. The focus of the methodology was on describing and enumerating ACS processes, components, and functions such that security engineers could: evaluate subversion options against the target; identify threat actor attributes and capabilities derived from each subversion option; and identify security controls and response countermeasures. The Use Cases document offered detailed methodology examples including an assessment of a Military Base SMR, an Autonomous System Decision Loop, and implementation of AR/SMR Machine Learning algorithms. Our proposal at the end of last year was to focus on implementation of subversion prototypes related to the last Use Case area: AR/SMR Machine Learning (ML) Algorithms. We included six attack scenarios in our Use Cases paper: a Poisoning Attack against ML functions implemented using an FPGA; a Trojaning Attack against ML classifiers exploiting the excitability of Nuclear Engineers; a Backdooring Attack against ML Training environments to ensure persistence of an attack vector; a False Positive Evasion Attack against multi-factor Access Control Systems using clever inputs; an Inference Attack against ML models by an Insider with access to the Operational environment; and an Adversarial Reprogramming Attack against a Material Access Control Video Surveillance System. At the beginning of this year these six attack scenarios were provided to our research teams at Georgia Tech and Idaho State University and each team successfully implemented a subversion attack against a ML implementation to include transient misclassifications. While this is a notable outcome from this type of research, this paper offers the reader insight into not only how to structure and execute these types of attacks, but into the thought process behind how the researcher investigated the problem space, performed initial algorithm implementation, and the trial-and-error behind arriving at the successful subversion prototypes. We include in this paper a set of associated Scenarios on how these subversion prototypes could be implemented and an initial set of guidance for AR/SMR architects, Nuclear Regulators, and Cyber Defenders to implement awareness and defense capabilities into their current operational portfolios.

42 ENGINEERING↗

Fourier-DeepONet: Fourier-enhanced deep operator networks for full waveform inversion with improved accuracy, generalizability, and robustness

In this article, full waveform inversion (FWI) infers the subsurface structure information from seismic waveform data by solving a non-convex optimization problem. Data-driven FWI has been increasingly studied with various neural network architectures to improve accuracy and computational efficiency. Nevertheless, the applicability of pre-trained neural networks is severely restricted by potential discrepancies between the source function used in the field survey and the one utilized during training. Here, we develop a Fourier-enhanced deep operator network (Fourier-DeepONet) for FWI with the generalization of seismic sources, including the frequencies and locations of sources. Specifically, we employ the Fourier neural operator as the decoder of DeepONet, and we utilize source parameters as one input of Fourier-DeepONet, facilitating the resolution of FWI with variable sources. To test Fourier-DeepONet, we develop three new and realistic FWI benchmark datasets (FWI-F, FWI-L, and FWI-FL) with varying source frequencies, locations, or both. Our experiments demonstrate that compared with existing data-driven FWI methods, Fourier-DeepONet obtains more accurate predictions of subsurface structures in a wide range of source parameters. Moreover, the proposed Fourier-DeepONet exhibits superior robustness when handling data with Gaussian noise or missing traces and sources with Gaussian noise, paving the way for more reliable and accurate subsurface imaging across diverse real conditions.

42 ENGINEERING↗

Pinatubo and pre-Pinatubo optical-depth spectra: Mauna Loa measurements, comparisons, inferred particle size distributions, radiative effects, and relationship to lidar data

The Ames airborne tracking sunphotometer was operated at the National Oceanic and Atmospheric Administration (NOAA) Mauna Loa Observatory (MLO) in 1991 and 1992 along with the NOAA Climate Monitoring and Diagnostics Laboratory (CMDL) automated tracking sunphotometer and lidar. June 1991 measurements provided calibrations, optical-depth spectra, and intercomparisons under relatively clean conditions; later measurements provided spectra and comparisons for the Pinatubo cloud plus calibration checks. June 1991 results are similar to previous MLO springtime measurements, with midvisible particle optical depth at the near-background level of 0.012 +/- 0.006 and no significant wavelength dependence in the measured range (lambda = 0.38 to 1.06 micrometers). The arrival of the Pinatubo cloud in July 1991 increased midvisible particle optical depth by more than an order of magnitude and changed the spectral shape of to an approximate power law with an exponent of about -1.4. By clearly September 1991, the spectrum was broadly peaked near 0.5 micrometers, and by July 1992, it was peaked near 0.8 micrometers. Our optical-depth spectra include corrections for diffuse light. NOAA- and Ames Research Center (ARC)-measured spectra are in good agreement. Columnar size distributions inverted from the spectra show that the initial (July 1991) post-Pinatubo cloud was relatively rich in small particles (r less than 0.25 micrometers), which were progressively depleted in the August-September 1991 and July 1992 periods. Conversely, both of the later periods had more of the optically efficient medium-sized particles (0.25 less than r less than 1 micrometers) than did the fresh July 1991 cloud. These changes are consistent with particle growth by condensation and coagulation. Photometer-inferred column backscatter values agree with those measured by the CMDL lidar on nearby nights. Combining lidar-measured backscatter profiles with photometer-derived backscatter-to-area ratios gives peak particle areas that could cause rapid heterogeneous loss of ozone, given sufficiently low particle acidity and suitable solar zenith angles (achieved at mid- to high latitudes). Top-of-troposphere radiative forcings for the September 1991 and July 1992 optical depths and size distributions over MLO are about -5 and -3 W/sq m, respectively (hence comparable in magnitude but opposite in sign to the radiative forcing caused by the increase in manmade greenhouse gases since the industrial revolution). Heating rates in the Pinatubo layer over MLO are 0.55 +/- 0.13 and 0.41 +/- 0.14 K/d for September 1991 and July 1992, respectively.

Russell, P. B.↗

ICE-RASSOR: Intelligent Capabilities Enhanced Regolith Advanced Surface Systems Operations Robot

NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for In-Situ Resource Utilization (ISRU)processing. RASSOR’s design enables it to efficiently collect and deposit regolith, return collected material for processing, and myriad related ISRU activities. To reliably perform these operations on the lunar surface, RASSOR software and sensory systems need to be robust and maximize the information extracted from a reduced sensor payload. Herein, we present preliminary findings from the Intelligent Capabilities Enhanced RASSOR project. We apply supervised learning using real data to estimate the soil mass collected without the need for mass flow rate monitors or other explicate sensing techniques. We also create a reduced-order simulation environment to develop autonomous trenching controllers via reinforcement learning and prototype state estimation architectures. Our initial results suggest that excavated regolith mass can be inferred within 2.9% RMS error of full scale, and reinforcement learning for autonomous operations has learned viable trenching strategies and helped identify desirable sensing capabilities, arrangements, and considerations. Future work includes regolith mass estimation during dynamic operation, expanding our simulation to more complex environments, and transfer learning from simulation to hardware.

machine learning↗

Atikokan Digital Twin: Machine learning in a biomass energy system

The Atikokan Generating Station, operated by Ontario Power Generation, has a 200 MW, biomass-fired tower boiler that operates on a dispatch schedule with a five-minute cycle. The boiler is generally operated in the range of 40–100 MW using two of five burner levels. In order to optimize boiler performance, we propose the implementation of a unique digital twin. Our digital twin abstraction couples Bayesian inference from science-based models and from observations (machine learning) with decision theory to predict operating-variable set points that optimize the physical asset (the boiler) in the presence of uncertainty (artificial intelligence). We focus this paper on the continuous Bayesian machine learning part of the Atikokan Digital Twin; we discuss decision theory in a companion paper. We identify and learn about 12 operational, model, and measured-output parameters and their uncertainties from high-fidelity, science-based simulations of the Atikokan boiler and from the observed measurements at the power plant. Since the goal of the Atikokan Digital Twin is to implement it online in real time, we require fast function evaluations for the quantities of interest extracted from the simulations in the Bayesian analysis. We use Gaussian process regression/interpolation to create accurate, robust surrogate models. We define the Bayesian priors and likelihood function and solve for the posterior distributions of the 12 parameters. Here we then propagate these distributions (i.e., parameters with uncertainty) into the predicted distributions of 790 quantities of interest to learn about the relative importance of various sources of error including experimental, model, and operating-parameter errors.

09 BIOMASS FUELS↗